Search Results for author: Chas Leichner

Found 3 papers, 2 papers with code

Pareto-Optimal Quantized ResNet Is Mostly 4-bit

4 code implementations7 May 2021 Amirali Abdolrashidi, Lisa Wang, Shivani Agrawal, Jonathan Malmaud, Oleg Rybakov, Chas Leichner, Lukasz Lew

In this work, we use ResNet as a case study to systematically investigate the effects of quantization on inference compute cost-quality tradeoff curves.

Quantization

Data-Free Neural Architecture Search via Recursive Label Calibration

no code implementations3 Dec 2021 Zechun Liu, Zhiqiang Shen, Yun Long, Eric Xing, Kwang-Ting Cheng, Chas Leichner

We identify that the NAS task requires the synthesized data (we target at image domain here) with enough semantics, diversity, and a minimal domain gap from the natural images.

Neural Architecture Search

MobileNetV4 - Universal Models for the Mobile Ecosystem

2 code implementations16 Apr 2024 Danfeng Qin, Chas Leichner, Manolis Delakis, Marco Fornoni, Shixin Luo, Fan Yang, Weijun Wang, Colby Banbury, Chengxi Ye, Berkin Akin, Vaibhav Aggarwal, Tenghui Zhu, Daniele Moro, Andrew Howard

We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices.

Neural Architecture Search

Cannot find the paper you are looking for? You can Submit a new open access paper.